Sixth Workshop on Language Technology for Equality, Diversity and Inclusion
(LT-EDI-2026)
at
The 64th Annual Meeting of the Association for Computational Linguistics (ACL) 2026
Place: San Diego, California, United States
Conference Date: July 02 - 07, 2026
Equality, Diversity, and Inclusion (EDI) are growing in importance in society, for ensuring fair representation, participation, and respect for all individuals regardless of identity. Language Technology (LT) systems play an increasingly pivotal role in shaping public discourse, enhancing accessibility, and fostering social participation. Biases across gender, race, religion, disability, sexual orientation, and intersectional identities continue to challenge NLP and AI systems, especially large language models trained on vast datasets. Recent research highlights not only the need for bias detection and mitigation but also for inclusive language generation, counter-narratives, fairness-aware evaluation, and explainable NLP systems. Addressing these issues requires resources, datasets, and tools that prioritize inclusivity, trustworthiness, and multicultural perspectives. This workshop will explore the critical challenges and innovative solutions for creating inclusive and identifying Large Language Models (LLMs). As LLMs become more integrated into our daily lives, addressing inherent biases in their training data and ensuring equitable, respectful, and culturally sensitive outputs is paramount. We invite researchers, developers, and ethicists to submit proposals that present novel methodologies for bias detection and mitigation, discuss frameworks for evaluating LLM inclusivity, or share case studies on developing fair and representative models The LT-EDI 2026 workshop will serve as a platform to advance these discussions, bringing together interdisciplinary researchers to design and evaluate LT that foster EDI across English and under-resourced languages.
Tagline: Towards Fair and Inclusive Language Technologies for All.
Call for Papers:
Following the success of the first five editions of the LTEDI 2026 workshop (LDK 2025, EACL 2024, RANLP 2023, ACL 2022. EACL 2021), the workshop aims to bring together researchers and practitioners working on NLP, LLMs and other AI fields with social scientists and interdisciplinary researchers. LT-EDI-2026 invites theoretical, empirical, and applied papers from the Natural Language Processing (NLP), Artificial Intelligence (AI), and interdisciplinary communities particularly those focusing on bias in language technologies. Topics of interest include, but are not limited to:
Datasets, and Benchmarks for Equality, Diversity, and Inclusion
Construction and annotation of datasets for EDI, including benchmarks for bias detection and mitigation.
Compilation of resources curated for fairness, inclusivity, and accessibility.
Methodologies for annotating intersectional identities (gender, race, disability, religion, sexual orientation, etc.).
Bias Detection and Mitigation in LLMs
Techniques for identifying, measuring, and mediating gender, racial, disability, and other societal biases in NLP and LLMs.
The impact of bias in deployed NLP/LLM systems
Gender-neutral modeling and representational fairness in LLMs
Detection and mitigation of intersectional biases including gender, racial, gender identity, disability, and other societal biases.
Advances in bias mitigation in large language models: in-context learning, prompt engineering, conditional text generation, and adversarial training.
Inclusive Language and Counter-Narratives for LLMs
Algorithms and resources for inclusive language generation with LLMs.
Counter-narrative modeling for combating toxicity, hate speech, and misinformation targeting marginalized communities.
Dialogue systems and multi-agent approaches that align with inclusivity goals.
Human-in-the-loop and participatory strategies for enhancing inclusiveness.
Multilingual and Multicultural Approaches for LLMs
Multicultural and multilingual LLMs and approaches
Speech and language recognition for minority and under-resourced groups
Code-mixed and cross-lingual approaches for inclusive technologies
Responsible, Explainable, and Trustworthy LLMs for EDI
Detecting and mitigating hallucinations, misinformation, and toxicity in LLM systems
Explainable and trustworthy LLMs
Evaluation frameworks incorporating ethics, accountability, and transparency
Laura Hollink
Scientific Staff Member, MT member, Group leader,
Human-Centered Data Analytics group at
CWI, Netherlands.